Online Shopping Research Articles

Predicting e-commerce product prices through the integration of variational mode decomposition and deep neural networks

Product prices frequently manifest nonlinear and nonstationary time-series attributes, indicating potential variations in their behavioral patterns over time. Conventional linear models may fall short in adequately capturing these intricate properties. In addressing this, the present study leverages the adaptive and non-recursive attributes of the Variational Mode Decomposition (VMD) methodology. It employs VMD to dissect the intricate time series into multiple Intrinsic Mode Functions (IMF). Subsequently, a method rooted in the minimum fuzzy entropy criterion is introduced for determining the optimal modal number (K) in the VMD decomposition process. This method effectively mitigates issues related to modal confusion and endpoint effects, thereby enhancing the decomposition efficacy of VMD. In the subsequent phase, deep neural networks (DNN) are harnessed to forecast the identified modes, with the cumulative modal predictions yielding the ultimate e-commerce product price prognostications. The predictive efficacy of the proposed Variational Mode Decomposition-deep neural network (VMD-DNN) decomposition model is assessed on three public datasets, wherein the mean absolute percentage error (MAPE) on the E-commerce Price Prediction Dataset and Online Retail Dataset is notably low at 0.6578 and 0.5414, respectively. This corresponds to a remarkable error reduction rate of 66.5% and 70.4%. Moreover, the VMD-DNN decomposition model excels in predicting e-commerce product prices through DNN, thereby amplifying the VMD decomposition capability by 4%. The VMD-DNN model attains superior results in terms of directional symmetry, boasting the highest Directional Symmetry (DS) score of 86.25. Notably, the forecasted trends across diverse price ranges closely mirror the actual trends.

Analysis of in-store crowdshipping in a stochastic dynamic pickup-and-delivery system

AbstractTo meet the increasing demands of home delivery resulting from the proliferation of internet shopping and compounded by the rising expectation of fast fulfillment (often within hours of request), companies seek new delivery methods supported by information and communication technologies. In this study, we consider a dispatching platform with delivery capacity consisting of a dedicated fleet of vehicles complemented by crowdsourced couriers. We consider the crowdsourced couriers to be in-store customers who, upon checking out of the store, declare themselves available to deliver one or more requests from e-shoppers. The role of the collaborative platform is to aggregate e-shopper orders from the participating businesses and then manage the routing for the pickup of the corresponding products at the physical stores and the subsequent deliveries to the e-shoppers’ locations. We model this dynamic stochastic pickup-and-delivery problem as a Markov decision process to represent the uncertainty in the e-shopper requests and in-store crowdshipper appearances. We adapt a real-time insertion method enhanced with a cost function approximation to account for differences in the temporal availability of the dedicated vehicles and in-store crowdshippers. We conduct computational experiments to demonstrate the conditions under which in-store crowdshippers provide a cost benefit.

Screening for contamination with genetically modified organisms in food, feed and their additives obtained in retail and online shops in Latvia

The aim of the study was to screen for contamination of food and feed products with genetically modified organisms (GMO) in several sample groups obtained from retail and online shops. The total number of samples was 171, including 67 of food, 26 feed, 27 additive, and 51 samples of dried pollen for human consumption. Detection and quantification of GMO in food and feed was performed according to the approved quantitative real-time PCR methods. Fermentation product samples were analyzed using screening for antimicrobial resistance genes, 16S RNA and ITS1 sequencing, isolation of bacterial cultures and whole genome sequencing. In total, GMO contamination was found in 12 samples (in 10.45% of food and in 19.23% of feed samples). A lower proportion of GMO containing samples were from the European Union (10.26 %) vs. samples from outside (17.02%), but none with ingredients of both origins. Non-compliant were three food and five feed samples. Of the 27 samples of food and feed additives and food supplements, 10 samples were possibly non-compliant, as they contained live bacteria with antimicrobial resistance genes, and seven of them contained possibly recombinant DNA. The study indicates presence of GMO contamination that emphasizes the need for further monitoring.

Exploring the Differences in Types of Commodities and Delivery Methods among Online Shoppers during the Early Stage of the COVID-19 Pandemic

During the early phases of the COVID-19 pandemic, the temporary limitations to in-store shopping during the lockdown period generated a significant increase in online shopping. During that period, the total spending amount and the number of online purchases increased across the whole population, although with rather heterogeneous patterns among various groups of consumers. This research examines the factors that can help explain the differences between users and non-users of online shopping in the U.S.A. during April and May 2020 to help understand the barriers to home-based shopping accessibility. The study uses data collected in the first survey wave of a longitudinal mobility study to analyze individual commodities and delivery options chosen for goods purchased online. Binomial logistic regression and Poisson regression models reveal differences in adopting e-shopping across various delivery channels, the frequency of purchase, and shipping used across commodities. In addition, a latent class cluster analysis identifies three heterogeneous groups of shoppers whose members differ mainly in income, age, education, neighborhood type, and technology attitudes. The results also highlight several differences in usage across crowdshipping markets and novel delivery options, such as in-store or locker pickup. The results also show variation in home-based accessibility across numerous factors during the pandemic.

Empowering Economic Growth in Balongdowo Village, Sidoarjo, East Java: Pioneering a Digital Tourism and Marketing Initiative

Balongdowo Village, recognized as the largest producer of Kupang in Sidoarjo Regency, has significant potential for economic development through its local seafood products. This community service program aims to enhance the economic sustainability of the village by empowering local businesses and introducing digital marketing strategies. The program focuses on promoting Kupang-based products through e-commerce platforms such as Tokopedia, Shopee, and Bukalapak, expanding market reach beyond the local area. Additionally, the initiative supports the development of a village information system portal to highlight the village’s profile, potential, and services. By integrating digital tools into marketing and village management, the project seeks to transform Balongdowo into a self-sufficient digital village. The program includes training sessions for local business owners and village officials on e-commerce usage, product presentation, and website management. The result is the successful establishment of online shops for local businesses and the launch of the Balongdowo village website, creating new opportunities for economic growth and improved public services.

Machine Learning in Predicting Consumer Behavior in Online Retail

Machine Learning in Predicting Consumer Behavior in Online Retail

The omnichannel effect: Evaluating consumer satisfaction in the wake of e-commerce closure among Bandung's MSMEs

This research delves into the impact of the government's closure of TikTok shop's online marketing interaction channel on MSMEs, emphasizing the reduction in offline interaction channels and resulting business losses. The study's primary objective is to dissect and assess the multifaceted omnichannel interaction framework, comprising online, offline, and cross channels, and its influence on consumer experience value and satisfaction. Conducted in Bandung, Indonesia, the research engaged 425 participants who interact through various marketing channels. Utilizing the partial least squares path model, the study deduces that while online and cross channels significantly influence experience value and consumer satisfaction, offline channels do not. This insight calls for a reevaluation of the TikTok shop closure decision, considering the profound role of satisfaction in purchasing decisions. The research, however, recognizes its limitations in terms of the temporal scope, analytical methods, and potential for hypothesis refinement. Future studies could broaden the geographic scope to incorporate diverse cities, offering insights shaped by varying local characteristics. Overall, the study contributes to the understanding of omnichannel interactions' effects on consumer satisfaction, presenting a nuanced perspective for academics and practitioners to enhance consumer shopping experiences.

Prevalence and correlates of e-cigarette source and use of e-cigarettes with nicotine: A case study of Mexico, where e-cigarettes are banned

BackgroundLow- and middle-income countries have increasingly banned e-cigarettes, as in Mexico. In these countries, little is known about where adults obtain e-cigarettes or who uses e-cigarettes with nicotine. MethodsData were analyzed from eight online surveys of Mexican adults who both smoked and used e-cigarettes (November 2018-March 2021; n = 2,060). For the e-cigarette they used most often, participants reported how they acquired it (social sources=reference; online purchase; vape shop purchase; other retail purchase) and if it contained nicotine (no=reference group; yes; don't know). Multinomial models regressed each of these outcomes on smoking- and e-cigarette-related factors, as well as sociodemographics. ResultsAlmost half the sample (45.9 %) reported obtaining their e-cigarettes from social sources, with online purchase being the second most common source (28.7 %). Being male, having recently attempted to quit smoking, and more frequent e-cigarette use were positively associated with purchasing e-cigarettes (vs social sources) across all venues. Most reported that their e-cigarettes contained nicotine (58.2 %), a third reported using e-cigarettes without nicotine (35.9 %), and some did not know (5.8 %). More frequent smoking and e-cigarette use, using closed e-cigarette devices and purchasing e-cigarettes online were positively associated with using e-cigarettes with nicotine. ConclusionsDespite Mexico's e-cigarette ban, adults who smoke access e-cigarettes through multiple sources, including online and vape shop purchases. Most participants reported using e-cigarettes with nicotine, though many did not or did not know.

Promised hassle time management in online retailing with fraudulent and regretful customers

Fraudulent customer return behavior, called “wardrobing,” incurs significant product return costs for online retailers. However, customers can also behave regretfully in online retailing, causing high product return costs. Consequently, we explore the combined effect of fraudulent and regretful customers in product returns. Research suggests implementing restrictive return policies to curb huge return costs due to fraudulent and regretful customer behaviors. One of the ways to implement a restrictive policy is by introducing hassle time. Consequently, retailers commit promised hassle times to customers, during which the retailers can approve the product returns and issue refunds. As a result, we determine how an online retailer can respond to regretful and fraudulent customers through promised hassle time while considering the stochastic nature of hassle time. In some situations, an online retailer might know that hassle time follows a specific probability distribution; in others, a retailer might not know the distribution. Therefore, we determine the optimal promised hassle time an online retailer must promise to regretful and fraudulent customers in each situation. For the first situation, we determine that a specific ratio, which we call the customer ratio, determines how the optimal promised hassle time changes with customers' fraud and regret levels. If the customer ratio is one, the optimal promised hassle time does not change; if it is greater than one, the optimal promised hassle time increases; and if it is less than one, the optimal promised hassle time decreases, with an increase in fraud and a decrease in regret levels. For the second situation, we propose a novel decision-making tool for online retailers, enabling them to optimize the promised hassle time. Finally, we generalize the results of our study to order cancellations with regretful customers, and shared mobility services.

How language arousal affects purchase intentions in online retailing? The role of virtual versus human influencers, language typicality, and trust

Despite the growing popularity of adopting various language strategies to boost business in online retailing and livestreaming, the effectiveness of such strategies employed by different (virtual vs. human) influencers is still unclear. This work examines how language arousal (high vs. low) interacts with influencer type (virtual vs. human) to impact consumer responses. With two scenario-based experiments, this research demonstrates that for virtual influencers, using high- (vs. low-) arousal language leads to stronger purchase intentions, whereas for human influencers, using high- (vs. low-) arousal language results in weaker purchase intentions. We also uncover a novel mechanism that language typicality and trust mediate this interaction effect in a serial manner. The theoretical and practical implications are also discussed.

An investigation into factors influencing consumer buying behaviour towards online shopping in Ghana

PurposeThe study aims to investigate the factors influencing consumer buying behaviour towards online shopping in Ghana.Design/methodology/approachA web survey was employed to test the concept mode. Perceived ease of use (PEOU), perceived usefulness (PU), perceived hedonic value (PHV) and perceived trust (PT) served as the independent variables, while consumer online buying behaviour (ConOBB) served as the dependent variable. The convenience sampling method was adopted to solicit data from 437 respondents. SPSS 26 and STATA 17 were the analytical tools used for the study. The analysis of the data includes a structural equation model (SEM) to assess the measurement and the influence of PEOU, PU, PHV and PT on ConOBB.FindingsThe study revealed that PEOU (Beta = 0.262), PU (Beta = 0.216), PHV (Beta = 0.354) and PT (Beta = 0.630) all had a positive relationship with ConOBB. The study also established that there are significant relationships between the factors (PEOU, PU, PHV and PT) and ConOBB in Ghana.Research limitations/implicationsThe study focuses on Ghanaian consumers and emphasises mainly online shopping factors, which are PEOU, PU, PHV and PT. E-commerce businesses face fierce competition due to the increased availability of websites and other online platforms. To attract potential customers, companies must streamline processes, ensure user-friendliness and create a user-friendly experience.Originality/valueThe uptake of online shopping in Ghana is relatively slow compared with other countries, particularly in Africa. Online shoppers and service providers in Ghana are keen to sustain the industry. However, there is currently a scarcity of empirical studies in Ghana that focus on specific factors that influence consumer online buying behaviour. This study offers a new model that offers novel insights into the specific factors that aid in consumer online shopping behaviour in Ghana. The measuring instrument, which was found to be reliable and valid, also serves as an added value that this study offers. Both the model and measuring instrument can assist managers offering online shopping opportunities to be able to measure and formulate strategies that would enhance consumer online shopping experiences. By adding perceived hedonic value and trust to the model, this study offers a unique extension of the technology acceptance model. Thus, the findings add to the body of knowledge in the field of online shopping, particularly in the context of Ghana.

Price, Marketing Communications and E-commerce Services on Consumer Purchase Intention in Online Shopping

General Background: The rise of technology and internet use has significantly influenced shopping behaviors in Indonesia, particularly with the growth of online shopping. Specific Background: Factors such as price, marketing communication, and e-commerce services are essential in shaping consumer purchasing decisions in this digital space. Knowledge Gap: Limited research has examined the combined impact of these variables on online purchase intentions. Aims: This study investigates the effects of price, marketing communication, and e-commerce services on consumer purchasing intentions. Results: Using a quantitative approach with 96 respondents, the analysis reveals that all independent variables significantly influence consumer purchase intentions in online shopping. Novelty: This research integrates multiple influencing factors into a single study, emphasizing their collective impact. Implications: Findings indicate that e-commerce platforms should focus on competitive pricing, effective marketing strategies, and quality services to enhance consumer purchase intentions, contributing to a thriving online retail environment. Highlights: Significant Influence: Price, marketing communication, and e-commerce services collectively impact consumer purchasing decisions in online shopping. Research Gap: This study fills the void by examining the combined effects of multiple factors on purchase intentions. Strategic Implications: E-commerce platforms should prioritize competitive pricing and effective marketing strategies to boost consumer engagement and sales. Keywords: Price, Marketing Communication, E-Commerce Services, Consumer Purchase Intention, Online Shopping

Assessing the impacts of peer-to-peer recommender system on online shopping: PLS-SEM approach

Peer-to-peer recommender systems play a critical role in online shopping in Vietnam. This paper aims to identify the relationship between Recommendation Quality and Purchase Intention and the moderating effects of Attitude and Trust on this relationship. Partial Least Squares Structural Equation Modeling was used as a research method. The sample consisted of 365 respondents who frequently use recommender system when shopping online. Data were collected using non-probability sampling method. The questionnaire is delivered to online customers who frequently rely on peer-to-peer recommender systems to make a purchase decision. The results show that Recommendation Transparency, Recommendation Accuracy, Recommendation Novelty, and Recommendation Diversity are positively related to Recommendation Quality. Consequently, Recommendation Quality has a positive impact on Attitude, Trust, and Purchase Intention. Besides, Attitude has a positive impact on online Purchase Intention. Trust also has a positive impact on online Purchase Intention. Practical implications are proposed to improve the impacts of peer-to-peer recommender systems on online shopping.

Self-Control and Emotional Maturity Reduce Consumptive Behavior in Women

Abstract: This research investigates the relationship between self-control and emotional maturity with consumptive behavior among women in Sumorame Village, Indonesia. General Background: Globalization has increased consumptive behavior, particularly among women reliant on branded goods and online shopping. Specific Background: Previous studies show significant levels of consumptive behavior among women, but few focus on rural communities like Sumorame. Knowledge Gap: This study addresses this gap by analyzing the impact of self-control and emotional maturity on consumptive behavior. Aims: The objective is to determine how these psychological factors influence purchasing tendencies. Results: A sample of 301 women revealed a significant negative correlation (rx1y = -0.368, p < 0.05; rx2y = -0.527, p < 0.05), indicating that higher self-control and emotional maturity lead to reduced consumptive behavior. Novelty: This research enhances understanding of economic behavior in rural contexts. Implications: Findings highlight the need for educational programs to improve self-control and emotional maturity, promoting better financial practices among women in Sumorame Village. Highlights: Higher self-control correlates with lower consumptive behavior in women. Emotional maturity significantly influences purchasing tendencies among women. Educational programs can enhance self-control and emotional maturity to improve financial practices. Keywords: Self-Control, Emotional Maturity, Consumptive Behavior, Women

The power of electronic Word of Mouth in inducing adoption of emerging technologies

This study examines the influence of electronic Word-of-Mouth (eWOM) on consumer expectations and intentions to adopt emerging technologies, specifically focusing on cryptocurrency payment methods. Employing the Elaboration Likelihood Model (ELM), the research utilizes Partial Least Squares Structural Equation Modeling (PLS-SEM) and Multi-Group Analysis (PLS-MGA) to analyze data from a diverse sample of 505 respondents sourced from MTurk. The findings reveal that the quality, consistency, and volume of eWOM significantly shape consumer expectations. Notably, the two-sidedness of online reviews does not have any substantial impact on both expectations and adoption behaviors toward cryptocurrency payment methods. Furthermore, factors such as the time spent online, and the frequency of online shopping were found to partially moderate the effects of eWOM on adoption behavior. This research contributes pioneering insights into the role of eWOM in influencing consumer attitudes towards cutting-edge technologies, extending existing knowledge beyond traditional consumer decisions to include technological adoption, particularly in digital finance. This offers valuable implications for technology firms and digital marketers aiming to harness eWOM to promote new technological solutions.

An Analysis of JD.com's Transportation System in Support of Operational and Logistics Activities

JD.com, also known as Jingdong, is China's largest online retailer and a leader in e-commerce, renowned for its vast selection of products, quality, and authenticity. Founded by CEO Richard Liu, JD.com has grown as a small electronics store into the third-largest Internet company globally, behind Amazon and Alphabet. It has pioneered advanced technologies like AI, robotics, and drones, transforming the retail industry. The company's extensive national distribution network covers 99% of China's population, allowing efficient deliveries, often within a day. JD.com's collaborations with Tencent, Walmart, and Google have further enhanced its logistics and customer experience. The platform's diverse transportation modes, including trucks, planes, and drones, ensure swift and reliable deliveries, while innovative self-driving trucks and automated warehouses streamline operations. JD.com continues to invest in software, data technologies, and sustainable transportation to maintain its competitive edge in the global e-commerce market.

Selling mode choice and return policy for advance selling in an e-commerce platform with social influence

Advance selling is increasingly employed to mitigate demand uncertainty, raise consumer awareness of products, and even exert social influence on subsequent sales. However, consumers may hesitate to pre-order products due to uncertainty about product valuation. As a response, sellers have begun implementing return policies and utilizing online retail platforms to alleviate the uncertainty. This study aims to investigate the interaction between return policies for advance selling and selling formats of e-commerce platforms considering the impact of social influence. We examine a two-period platform supply chain that includes agency selling, reselling, and hybrid selling formats with and without return policies. Using game theory models, we analyze pricing decisions and profits of each player under six possible scenarios. The results indicate that the manufacturer consistently prefers adopting a Money-Back Guarantee (MBG) return policy regardless of the selling format. However, the MBG return policy is not always advantageous for the platform, except in the case of low social influence. In such a case, the platform may implement the MBG return policy to boost advance sales, thereby enhancing the penetration power from advance sales to regular sales. Regarding selling formats, the platform and the manufacturer opt for the reselling and agency selling, respectively, when the commission rate is low; otherwise, they adopt the agency selling and hybrid selling, respectively. Furthermore, we explore the impact of critical drivers on the pricing decisions and profits within the platform supply chain. Our study offers valuable insights into implementing return policies and determining selling formats.

Physical stores versus physical showrooms: Channel structures of online retailers

To meet consumers’ expectations for experiential shopping, an increasing number of online retailers are expanding offline channels, with physical showrooms and physical showrooms emerging as the two most popular offline channel modes. Both channels can match consumers’ demand for on-site experiences. However, the two modes differ in terms of service cost, demand promotion efficiency, and channel differentiation generation. The article considers three channel structures: a single online channel, an online channel with physical stores, and an online channel with physical showrooms, as well as two scenarios: non-competitive and competitive. This study examines whether online retailers should integrate offline channels and which offline channel mode they should use by comparing the profit changes of themselves and rivals when three channel structures are adopted in two scenarios. It is found that: (i) If there is a significant difference between the online and physical store channels, providing physical stores help online retailer raise profits. If the physical showroom is highly effective at promoting demand, omnichannel retailers will dominate the entire online market, and expanding physical showrooms is always profitable; (ii) Whether in a competitive or non-competitive environment, online retailers should weigh channel differentiation and the efficiency of the offline channel modes in promoting demand to select the best channel mode; (iii) Due to channel differentiation, online retailers’ creation of physical stores, as well as increasing competition among physical stores, will have no impact on rival retailers. However, providing physical showrooms will result in lower sales volume and revenue for rival retailers.

Food for thought: The intersection between SNAP stigma, food insecurity, and gender

The Supplemental Nutrition Assistance Program (SNAP) helps millions of families with low incomes to afford and purchase food each year. Prior research has noted that welfare stigma—negative stereotypes about people who participate in public assistance programs—can limit SNAP participation. Stigma may also contribute to worse mental health among subgroups like male participants; qualitative evidence suggests males may struggle to accept public assistance benefits due to norms surrounding gender roles. Yet there is little research about who is most likely to experience stigma, how stigma relates to food insecurity, whether this relationship varies by gender identity, and whether stigma is associated with online shopping (which may protect against stigma). To address these gaps, we analyzed a national survey of 1383 SNAP participants about their experiences of SNAP stigma, food insecurity, and online shopping. In adjusted models, we found that male participants had 40% higher odds (95% CI: 1.09–1.80) of reporting any stigma experience compared to female participants. SNAP participants reporting stigma had over three times the odds (OR: 3.54, 95% CI: 2.60–4.81) of reporting food insecurity relative to those not reporting stigma, and male participants reporting stigma had nearly three times higher odds of food insecurity than female participants reporting stigma (OR: 2.94, 95% CI: 1.53, 5.66). In addition, stigma was not significantly associated with shopping online or using SNAP benefits online. In this national sample of SNAP participants, male respondents had greater odds of welfare stigma, experiences of stigma were associated with greater odds of food insecurity, male respondents experiencing stigma had greater odds of food insecurity compared to female respondents, and stigma was not associated with online shopping behaviors. Efforts to reframe public assistance may be needed to destigmatize programs like SNAP to both improve program uptake among non-participants and improve health outcomes among participants.

Deliberate shortage in live-streaming commerce

Live-streaming commerce has gained significant traction in recent years as an additional channel employed by online retailers to engage consumers in real-time interactions. However, it is essential to highlight the growing prevalence of limited sales as a popular marketing strategy within these live-streaming channels, resulting in an inability to fulfill all consumer demands. Surprisingly, this phenomenon has gone largely unnoticed in previous literature. This paper aims to bridge this gap by delving into the impact of product shortages within the realm of live-streaming commerce. To accomplish this objective, we introduce a stylized model that captures the strategic interactions between online retailers and consumers within live-streaming channels featuring rationed product availability. Our findings reveal that the online retailer’s profit exhibits a unimodal trend concerning the quantity of products offered in the live-streaming channel when the product value falls within a non-extreme range. In simpler terms, deliberately limiting product availability in live-streaming commerce can lead to significantly higher profits, incentivizing retailers to implement rationing strategies. Moreover, contrary to conventional expectations that consumers anticipate a greater supply of products than the retailer intends to provide, we uncover that consumers expect a lower quantity when the potential product value is relatively small. Finally, our research highlights that while live-streaming channels attract consumers with high patience, encouraging their engagement, impatient consumers who favor traditional online channels may face long-term adverse effects due to the retailer’s strategic pricing response. We validate the robustness of our main findings by exploring various extensions, such as the influence of strategic waiting behavior, advertising effects and enhanced perceived product value.